arXiv AI
Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 26
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
The paper evaluates the use of large language models (LLMs) as judges for assessing conversational voice agents, comparing human judgments with GPT‑4.1 and GPT‑5 across telecom and retail interactions. It examines agreement, metric‑level correlations, and consistency across three evaluation configurations (p0, p1, p2) to determine how reliably LLMs can judge conversational quality and safety. The study finds that LLM‑based evaluation can be effective but its reliability varies by metric and configuration, suggesting a hybrid approach where LLMs handle scalable assessment while humans focus on metrics requiring contextual interpretation.
arXiv AI
Sep 10
AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation
arXiv:2609.06991v1 Announce Type: cross Abstract: Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses...
arXiv AI
Jun 18
Signals of Provenance: Practices & Challenges of Navigating Indicators in AI-Generated Media for Sighted and Blind Individuals
arXiv:2505. 16057v2 Announce Type: replace-cross Abstract: AI-Generated (AIG) content has become increasingly widespread by recent advances in generative models and the easy-to-use tools that have significantly lowered the technical barriers for producing highly realistic audio, images, and videos through simple natural language prompts.
arXiv Computer Vision
Sep 24
Can Vision-Language Models Analyze Human-Centered Video? Mapping Model Capabilities and Human-AI Collaborative Workflows
The paper investigates when vision‑language models (VLMs) can independently analyze human‑centered video and when human oversight is still needed. By reviewing 1,702 CHI 2026 papers, the authors develop a five‑dimensional taxonomy of video annotation tasks and build a benchmark of 15 representative tasks. Experiments show that VLMs alone achieve near‑human accuracy (HNS = 97.0), while human verification of VLM outputs yields the highest accuracy (HNS = 121.5) and significantly reduces annotation time and cost.
arXiv AI
Sep 7
PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation
PRISM‑Bench is an audio‑centric diagnostic benchmark for text‑to‑audio‑video generation, built from 900 human‑verified samples. It evaluates audio along two axes—audio type (speech, music, sound) and sound‑source visibility (on‑screen vs. off‑screen)—across four perceptual dimensions (audio‑visual coherence, audio quality, audio expressiveness, and prompt following) using 35 fine‑grained criteria. The benchmark employs an enhanced MLLM‑as‑a‑Judge protocol that aligns strongly with human raters, revealing a performance gap between frontier and open‑source T2AV models and highlighting overfitting to perceptual fidelity while struggling with complex grounding and control tasks, especially for music and synchronized on‑screen audio.
arXiv Computer Vision
Sep 10
Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition
arXiv:2609.10394v1 Announce Type: cross Abstract: Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the...